TL;DR:
- UW-Madison researchers and NFL player Matt Henningsen collaborate on an MRI machine-learning project.
- The project focuses on identifying and addressing intracerebral hemorrhages (ICH) in the brain.
- Professor Walter Block leads the research team, developing a specialized algorithm for surgeons.
- Tom Lilieholm, a PhD candidate, achieves impressive accuracy in clot and edema segmentation.
- Matt Henningsen, a former UW-Madison student and Denver Broncos player, contributes over 100 hours of data collection.
- The project holds potential for future advancements in diagnosing traumatic brain injuries.
Main AI News:
In a remarkable collaboration, the University of Wisconsin-Madison researchers and Denver Broncos player Matt Henningsen have embarked on a groundbreaking project centered around a cutting-edge MRI machine-learning network. This initiative aims to revolutionize the way medical professionals identify and address intracerebral hemorrhages (ICH) or bleeding within the brain.
Led by Professor Walter Block, an expert in medical physics and biomedical engineering, the research team has developed a specialized algorithm that empowers surgeons with the critical information required for swift and precise brain bleed extraction. The key challenge lies in visualizing and quantifying the hemorrhage, ensuring that surgeons have the necessary insights at their disposal. According to Block, “The trick is to visualize it and quantify it so that the surgeon has the information they need.”
Tom Lilieholm, a PhD candidate and the lead author of this groundbreaking research, played a pivotal role in creating the algorithm for the new color-coded MRI machine-learning network. Lilieholm reports impressive results, stating, “We got pretty high accurate segmentations out of the machine here, 96% accurate clot, 81% accurate edema.” He showcased one of the study’s MRI slides, which can now reveal to a surgeon in under a minute the extent of the hemorrhage that can be safely removed. “It’s really kind of useful to have that and to have robust data to compare against,” added Lilieholm.
What makes this collaboration even more compelling is the involvement of NFL player Matt Henningsen, a Menomonee Falls native and former UW-Madison standout both on the football field and in the classroom. Armed with bachelor’s and master’s degrees from the university, Henningsen has taken on the task of identifying the precise location of the intracerebral hemorrhage and segmenting both the clot and the edema surrounding it. He meticulously analyzes every layer of the MRI image, contributing over 100 hours of data collection to this vital research.
Henningsen is enthusiastic about the opportunity to be part of this significant endeavor and hopes that it will eventually lead to advancements in the diagnosis of traumatic brain injuries, a concern close to his heart as a football professional. “You can’t diagnose concussion with an MRI currently,” he noted. “But I mean, maybe in the future, if you’re able to, you can use machine learning to potentially detect certain abnormalities that the human eye couldn’t necessarily detect or things of that sort. Maybe we could get somewhere.” This collaboration between academic excellence and athletic prowess holds the promise of transformative outcomes in the realm of brain injury diagnosis and treatment.
Conclusion:
This innovative collaboration between academia and professional sports has the potential to significantly impact the medical market. The development of a specialized MRI machine-learning network for identifying brain hemorrhages could lead to improved diagnosis and treatment of brain injuries, opening up new opportunities for medical technology companies and healthcare providers in this rapidly evolving field.
